使用图谱配准和统计纹理先验的超声图像自动三维分割
Automatic 3D Segmentation of Ultrasound Images Using Atlas Registration and Statistical Texture Prior.
作者信息
Yang Xiaofeng, Schuster David, Master Viraj, Nieh Peter, Fenster Aaron, Fei Baowei
机构信息
Department of Radiology, Emory University, Atlanta, GA, USA.
出版信息
Proc SPIE Int Soc Opt Eng. 2011;7964. doi: 10.1117/12.877888. Epub 2011 Mar 1.
Abstract
We are developing a molecular image-directed, 3D ultrasound-guided, targeted biopsy system for improved detection of prostate cancer. In this paper, we propose an automatic 3D segmentation method for transrectal ultrasound (TRUS) images, which is based on multi-atlas registration and statistical texture prior. The atlas database includes registered TRUS images from previous patients and their segmented prostate surfaces. Three orthogonal Gabor filter banks are used to extract texture features from each image in the database. Patient-specific Gabor features from the atlas database are used to train kernel support vector machines (KSVMs) and then to segment the prostate image from a new patient. The segmentation method was tested in TRUS data from 5 patients. The average surface distance between our method and manual segmentation is 1.61 ± 0.35 mm, indicating that the atlas-based automatic segmentation method works well and could be used for 3D ultrasound-guided prostate biopsy.
摘要
我们正在开发一种分子图像引导、三维超声引导的靶向活检系统，以提高前列腺癌的检测率。在本文中，我们提出了一种基于多图谱配准和统计纹理先验的经直肠超声（TRUS）图像自动三维分割方法。图谱数据库包括来自先前患者的配准TRUS图像及其分割的前列腺表面。使用三个正交的Gabor滤波器组从数据库中的每个图像中提取纹理特征。来自图谱数据库的特定患者Gabor特征用于训练核支持向量机（KSVM），然后对新患者的前列腺图像进行分割。该分割方法在5名患者的TRUS数据中进行了测试。我们的方法与手动分割之间的平均表面距离为1.61±0.35毫米，表明基于图谱的自动分割方法效果良好，可用于三维超声引导的前列腺活检。
相似文献
1
Automatic 3D Segmentation of Ultrasound Images Using Atlas Registration and Statistical Texture Prior.使用图谱配准和统计纹理先验的超声图像自动三维分割
Proc SPIE Int Soc Opt Eng. 2011;7964. doi: 10.1117/12.877888. Epub 2011 Mar 1.
2
3D Prostate Segmentation of Ultrasound Images Combining Longitudinal Image Registration and Machine Learning.结合纵向图像配准和机器学习的超声图像三维前列腺分割
Proc SPIE Int Soc Opt Eng. 2012 Feb 23;8316:83162O. doi: 10.1117/12.912188.
3
3D ultrasound image segmentation using wavelet support vector machines.基于小波支持向量机的三维超声图像分割。
Med Phys. 2012 Jun;39(6):2972-84. doi: 10.1118/1.4709607.
4
A Molecular Image-directed, 3D Ultrasound-guided Biopsy System for the Prostate.一种用于前列腺的分子影像引导、三维超声引导活检系统。
Proc SPIE Int Soc Opt Eng. 2012;2012. doi: 10.1117/12.912182. Epub 2012 Feb 16.
5
Automatic prostate segmentation using deep learning on clinically diverse 3D transrectal ultrasound images.基于临床多样的三维经直肠超声图像，利用深度学习进行前列腺自动分割。
Med Phys. 2020 Jun;47(6):2413-2426. doi: 10.1002/mp.14134. Epub 2020 Apr 8.
6
A PET/CT Directed, 3D Ultrasound-Guided Biopsy System for Prostate Cancer.一种用于前列腺癌的PET/CT引导的三维超声引导活检系统。
Prostate Cancer Imaging (2011). 2011;6363:100-108. doi: 10.1007/978-3-642-23944-1_11.
7
Adaptation of a 3D prostate cancer atlas for transrectal ultrasound guided target-specific biopsy.一种用于经直肠超声引导下靶向活检的三维前列腺癌图谱的适配
Phys Med Biol. 2008 Oct 21;53(20):N397-406. doi: 10.1088/0031-9155/53/20/N03. Epub 2008 Sep 30.
8
Three-dimensional prostate segmentation using level set with shape constraint based on rotational slices for 3D end-firing TRUS guided biopsy.基于旋转切片的带形状约束水平集的三维前列腺分割用于 3D 端射式 TRUS 引导活检。
Med Phys. 2013 Jul;40(7):072903. doi: 10.1118/1.4810968.
9
Deep Learning for Real-time, Automatic, and Scanner-adapted Prostate (Zone) Segmentation of Transrectal Ultrasound, for Example, Magnetic Resonance Imaging-transrectal Ultrasound Fusion Prostate Biopsy.深度学习用于实时、自动和适应扫描仪的直肠超声前列腺（区域）分割，例如，磁共振成像-直肠超声融合前列腺活检。
Eur Urol Focus. 2021 Jan;7(1):78-85. doi: 10.1016/j.euf.2019.04.009. Epub 2019 Apr 23.
10
Random Walk Based Segmentation for the Prostate on 3D Transrectal Ultrasound Images.基于随机游走的三维经直肠超声图像前列腺分割
Proc SPIE Int Soc Opt Eng. 2016 Feb 27;9786. doi: 10.1117/12.2216526. Epub 2016 Mar 18.
引用本文的文献
1
Proposal for computer-aided diagnosis based on ultrasound images of the kidney: is it possible to compare shades of gray among such images?基于肾脏超声图像的计算机辅助诊断方案：能否比较此类图像中的灰度？
Radiol Bras. 2021 Jan-Feb;54(1):27-32. doi: 10.1590/0100-3984.2019.0138.
2
Deep learning in medical image registration: a review.深度学习在医学图像配准中的应用：综述。
Phys Med Biol. 2020 Oct 22;65(20):20TR01. doi: 10.1088/1361-6560/ab843e.
3
The Stacked-Ellipse Algorithm: An Ultrasound-Based 3-D Uterine Segmentation Tool for Enabling Adaptive Radiotherapy for Uterine Cervix Cancer.堆叠椭圆算法：一种基于超声的 3D 子宫分段工具，用于实现宫颈癌的自适应放疗。
Ultrasound Med Biol. 2020 Apr;46(4):1040-1052. doi: 10.1016/j.ultrasmedbio.2019.09.001. Epub 2020 Jan 8.
4
3D Transrectal Ultrasound (TRUS) Prostate Segmentation Based on Optimal Feature Learning Framework.基于最优特征学习框架的3D经直肠超声（TRUS）前列腺分割
Proc SPIE Int Soc Opt Eng. 2016 Feb-Mar;9784. doi: 10.1117/12.2216396. Epub 2016 Mar 21.
5
A 3D Neurovascular Bundles Segmentation Method based on MR-TRUS Deformable Registration.基于磁共振弹性成像-经直肠超声弹性成像变形配准的三维神经血管束分割方法
Proc SPIE Int Soc Opt Eng. 2015 Feb;9413. doi: 10.1117/12.2077828. Epub 2015 Mar 20.
6
A MR-TRUS Registration Method for Ultrasound-Guided Prostate Interventions.一种用于超声引导下前列腺介入治疗的磁共振-经直肠超声配准方法。
Proc SPIE Int Soc Opt Eng. 2015 Feb;9415. doi: 10.1117/12.2077825. Epub 2015 Mar 18.
7
Patch-Based Label Fusion for Automatic Multi-Atlas-Based Prostate Segmentation in MR Images.基于补丁的标签融合用于磁共振图像中基于多图谱的前列腺自动分割
Proc SPIE Int Soc Opt Eng. 2016 Feb-Mar;9786. doi: 10.1117/12.2216424. Epub 2016 Mar 18.
8
Ultrasound prostate segmentation based on multidirectional deeply supervised V-Net.基于多方向深度监督 V-Net 的前列腺超声图像分割。
Med Phys. 2019 Jul;46(7):3194-3206. doi: 10.1002/mp.13577. Epub 2019 May 29.
9
Deeply supervised 3D fully convolutional networks with group dilated convolution for automatic MRI prostate segmentation.基于深度监督的三维全卷积网络与分组空洞卷积在自动 MRI 前列腺分割中的应用。
Med Phys. 2019 Apr;46(4):1707-1718. doi: 10.1002/mp.13416. Epub 2019 Feb 19.
10
A random walk-based segmentation framework for 3D ultrasound images of the prostate.基于随机游走的前列腺三维超声图像分割框架。
Med Phys. 2017 Oct;44(10):5128-5142. doi: 10.1002/mp.12396. Epub 2017 Jul 18.
本文引用的文献
1
A Minimal Path Searching Approach for Active Shape Model (ASM)-based Segmentation of the Lung.一种基于主动形状模型（ASM）的肺部分割的最小路径搜索方法。
Proc SPIE Int Soc Opt Eng. 2009 Mar 27;7259. doi: 10.1117/12.812575.
2
Multiscale Fuzzy C-Means Image Classification for Multiple Weighted MR Images for the Assessment of Photodynamic Therapy in Mice.用于评估小鼠光动力疗法的多加权磁共振图像的多尺度模糊C均值图像分类
Proc SPIE Int Soc Opt Eng. 2007 Mar 8;6512. doi: 10.1117/12.710188.
3
3D Non-rigid Registration Using Surface and Local Salient Features for Transrectal Ultrasound Image-guided Prostate Biopsy.基于表面和局部显著特征的3D非刚性配准在经直肠超声图像引导前列腺活检中的应用
Proc SPIE Int Soc Opt Eng. 2011 Mar 1;7964:79642V. doi: 10.1117/12.878153.
4
3D Segmentation of Prostate Ultrasound images Using Wavelet Transform.基于小波变换的前列腺超声图像三维分割
Proc SPIE Int Soc Opt Eng. 2011;7962:79622K. doi: 10.1117/12.878072. Epub 2011 Mar 14.
5
Detection and analysis of the intestinal ischemia using visible and invisible hyperspectral imaging.利用可见和不可见高光谱成像检测和分析肠道缺血。
IEEE Trans Biomed Eng. 2010 Aug;57(8):2011-7. doi: 10.1109/TBME.2010.2049110. Epub 2010 May 10.
6
Discrete deformable model guided by partial active shape model for TRUS image segmentation.基于部分主动形状模型的离散变形模型在 TRUS 图像分割中的应用。
IEEE Trans Biomed Eng. 2010 May;57(5):1158-66. doi: 10.1109/TBME.2009.2037491. Epub 2010 Feb 5.
7
A modified fuzzy C-means classification method using a multiscale diffusion filtering scheme.一种使用多尺度扩散滤波方案的改进型模糊C均值分类方法。
Med Image Anal. 2009 Apr;13(2):193-202. doi: 10.1016/j.media.2008.06.014. Epub 2008 Jul 5.
8
Segmentation of prostate from 3-D ultrasound volumes using shape and intensity priors in level set framework.在水平集框架中使用形状和强度先验知识从三维超声容积中分割前列腺。
Conf Proc IEEE Eng Med Biol Soc. 2006;2006:2341-4. doi: 10.1109/IEMBS.2006.260000.
9
Prostate segmentation in 2D ultrasound images using image warping and ellipse fitting.使用图像变形和椭圆拟合在二维超声图像中进行前列腺分割。
Med Image Comput Comput Assist Interv. 2006;9(Pt 2):17-24. doi: 10.1007/11866763_3.
10
Ultrasound image segmentation: a survey.超声图像分割：综述
IEEE Trans Med Imaging. 2006 Aug;25(8):987-1010. doi: 10.1109/tmi.2006.877092.
Zotero 插件